Package org.htmlparser.util

Examples of org.htmlparser.util.NodeList

940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
    }
   
    private void parseCategory(Node categoryNode, List<Category> categories) throws ParserException {
      NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
     
      NodeList links = new NodeList();
      categoryNode.collectInto(links, linkFilter);
     
      if (links.size() == 0) {
        return;
      }
     
        Category parent = null;
      NodeIterator iter = links.elements();
        while (iter.hasMoreNodes()) {
          LinkTag link = (LinkTag)iter.nextNode();
          Category category = new Category();
          category.setTitle(NodeUtils.getTextData(link));
          category.setId(link.getLink().replaceAll(".*/movieGenres/(.*?)", "$1"));
View Full Code Here
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
            parser.extractAllNodesThatMatch(infoCollector);
           
            String selectedPage = NodeUtils.getTextData(infoCollector.getNode(0));
            if (selectedPage != null && selectedPage.equals(Integer.toString(page))) {
           
                NodeList browseNodes = infoCollector.getNodeList(1);
               
                if (browseNodes.size() > 1) {
                    NodeIterator iter = browseNodes.elements();
                   
                    while (iter.hasMoreNodes()) {
                        MovieItem item = parseMovieSearch(iter.nextNode());
                        if (item != null) {
                            items.add(item);
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
    public void parseHtml(URI uri, InputStream content)
    {
        ByteArrayOutputStream output = null;  //####TODO: Add in MIME type detection to this stream
        Parser                parser = null;
        NodeFilter            filter = null;
        NodeList              list   = null;
       
       
        if (uriFilter.isURIInternal(uri) && content != null)
        {
            log.debug("Parsing HTML from URI " + uri.toString());
       
            try
            {
                log.debug("Copying content.");
       
                output = new ByteArrayOutputStream();
                IOUtils.copy(content, output);
               
                log.debug("Creating filter.");
       
                //####TODO: Dependency inject this crap
                filter = new AndFilter(new NodeClassFilter(LinkTag.class),
                                       new NodeFilter()
                                       {
                                           public boolean accept(Node node)
                                           {
                                               return(!((LinkTag)node).isMailLink());
                                           }
                                       });
               
                log.debug("Creating parser.");
       
                parser = new Parser(output.toString());
               
                log.debug("Extracting all nodes that match the filter.");
       
                list = parser.extractAllNodesThatMatch(filter);
               
                log.debug("About to iterate through the matching nodes, count=" + list.size());
       
                for (int i = 0; i < list.size(); i++)
                {
                    log.debug("Loop=" + i);
       
                    Node                linkTagNode = list.elementAt(i);
                    String              linkTag     = linkTagNode.toHtml();
                    URI                 targetURI   = parseLinkTag(uri, linkTagNode);
                    Map<String, String> properties  = new HashMap<String, String>();
                   
                    properties.put("linkTagText", linkTag);
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
        return;
      }

      myKey.set(key.get());

      NodeList nl;
      try {
        // initialize HTML parser
        parser.setInputHTML(doc.getContent());

        // parse the document
        nl = parser.parse(filter);
      } catch (ParserException e) {
        context.getCounter(LinkCounter.PARSER_FAILED).increment(1);
        myValue.setDocid(doc.getDocid());
        myValue.setContent("<DOC>\n<DOCNO>" + doc.getDocid() + "</DOCNO>\n<DOC>");
        context.write(myKey, myValue);
        return;
      } catch (StackOverflowError e) {
        context.getCounter(LinkCounter.PARSER_FAILED).increment(1);
        myValue.setDocid(doc.getDocid());
        myValue.setContent("<DOC>\n<DOCNO>" + doc.getDocid() + "</DOCNO>\n<DOC>");
        context.write(myKey, myValue);
        return;
      }

      strBuf.setLength(0);
      strBuf.append("<DOC>\n<DOCNO>");
      strBuf.append(doc.getDocid());
      strBuf.append("</DOCNO>\n");

      for (int i = 0; i < nl.size(); i++) {
        strBuf.append(nl.elementAt(i).toHtml()).append("\n");
      }
      strBuf.append("</DOC>\n");

      // create output document
      myValue.setDocid(doc.getDocid());
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
        parser.setInputHTML(doc.getContent()); // initializing the
        // parser with new HTML
        // content

        // Setting base URL for the current document
        NodeList nl = parser.parse(null);
        BaseHrefTag baseTag = new BaseHrefTag();
        baseTag.setBaseUrl(base);
        nl.add(baseTag);

        // re-initializing the parser with the fixed content
        parser.setInputHTML(nl.toHtml());

        // listing all LinkTag nodes
        list = parser.extractAllNodesThatMatch(filter);
      }
      catch (ParserException e)
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
      try {
        // initializing the parser with new content
        parser.setInputHTML(doc.getContent());

        // Setting base URL for the current document
        NodeList nl = parser.parse(null);
        BaseHrefTag baseTag = new BaseHrefTag();
        baseTag.setBaseUrl(base);
        nl.add(baseTag);

        // re-initializing the parser with the correct content
        parser.setInputHTML(nl.toHtml());

        // listing all LinkTag nodes
        list = parser.extractAllNodesThatMatch(filter);
      } catch (ParserException e) {
        reporter.incrCounter(LinkCounter.PARSER_FAILED, 1);
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
     * @exception ParserException If the parse fails.
     */
    protected URL[] extractLinks () throws ParserException
    {
        NodeFilter filter;
        NodeList list;
        Vector vector;
        LinkTag link;
        URL[] ret;

        mParser.reset ();
        filter = new NodeClassFilter (LinkTag.class);
        try
        {
            list = mParser.extractAllNodesThatMatch (filter);
        }
        catch (EncodingChangeException ece)
        {
            mParser.reset ();
            list = mParser.extractAllNodesThatMatch (filter);
        }
        vector = new Vector();
        for (int i = 0; i < list.size (); i++)
            try
            {
                link = (LinkTag)list.elementAt (i);
                vector.add(new URL (link.getLink ()));
            }
            catch (MalformedURLException murle)
            {
                //vector.remove (i);
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
     * Assign the <code>Nodes</code> property, firing the property change.
     * @param nodes The new value of the <code>Nodes</code> property.
     */
    protected void updateNodes (NodeList nodes)
    {
        NodeList oldValue;
        String oldText;
        String newText;

        if ((null == mNodes) || !mNodes.equals (nodes))
        {
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    protected NodeList applyFilters ()
        throws
            ParserException
    {
        NodeFilter[] filters;
        NodeList ret;

        ret = mParser.parse (null);
        filters = getFilters ();
        if (null != filters)
            for (int i = 0; i < filters.length; i++)
                ret = ret.extractAllNodesThatMatch (filters[i], mRecursive);

        return (ret);
    }
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
     * Fetch the URL contents and filter it.
     * Only do work if there is a valid parser with it's URL set.
     */
    protected void setNodes ()
    {
        NodeList list;

        if (null != getURL ())
            try
            {
                list = applyFilters ();
                updateNodes (list);
            }
            catch (EncodingChangeException ece)
            {
                try
                {   // try again with the encoding now in force
                    mParser.reset ();
                    list = applyFilters ();
                    updateNodes (list);
                }
                catch (ParserException pe)
                {
                    updateNodes (new NodeList ());
                }
             }
            catch (ParserException pe)
            {
                updateNodes (new NodeList ());
            }
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.util.NodeList

  • com.almilli.htmlparser.NodeCollector
  • com.almilli.movierentals.blockbuster.BlockbusterService
  • com.almilli.movierentals.netflix.NetFlixService
  • com.knowgate.hipermail.HtmlMimeBodyPart
  • com.lanyuan.util.HttpClientUtils
  • com.vgo.movie.thread.DetailFilmThread
  • com.waxayaz.TomcatMI.core.utils.repoManager.TomcatRepositoryManager
  • fitnesse.fixtures.PageDriver
  • fitnesse.slim.converters.MapEditor
  • fitnesse.testsystems.slim.HtmlSlimTestSystem
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.